Zobrazeno 1 - 10
of 190
pro vyhledávání: '"Sarkar, Sayan"'
Autor:
Parida, Shantipriya, Abdulmumin, Idris, Muhammad, Shamsuddeen Hassan, Bose, Aneesh, Kohli, Guneet Singh, Ahmad, Ibrahim Said, Kotwal, Ketan, Sarkar, Sayan Deb, Bojar, Ondřej, Kakudi, Habeebah Adamu
This paper presents HaVQA, the first multimodal dataset for visual question-answering (VQA) tasks in the Hausa language. The dataset was created by manually translating 6,022 English question-answer pairs, which are associated with 1,555 unique image
Externí odkaz:
http://arxiv.org/abs/2305.17690
Building 3D scene graphs has recently emerged as a topic in scene representation for several embodied AI applications to represent the world in a structured and rich manner. With their increased use in solving downstream tasks (eg, navigation and roo
Externí odkaz:
http://arxiv.org/abs/2304.14880
The presented study aims to estimate blood pressure (BP) using photoplethysmogram (PPG) signals while employing multiple machine learning models. The study proposes a novel algorithm for signal reconstruction, which utilizes the semi-classical signal
Externí odkaz:
http://arxiv.org/abs/2301.08439
All-optical devices are essential for next generation ultrafast, ultralow-power and ultrahigh bandwidth information processing systems. Silicon microring resonators (SiMRR) provide a versatile platform for all-optical switching and CMOS-compatible co
Externí odkaz:
http://arxiv.org/abs/2210.04293
Photoplethysmography (PPG) signal comprises physiological information related to cardiorespiratory health. However, while recording, these PPG signals are easily corrupted by motion artifacts and body movements, leading to noise enriched, poor qualit
Externí odkaz:
http://arxiv.org/abs/2202.00606
In electromagnetic analysis, the finite element and boundary element methods jointly known as 'FEM-BEM coupling' is applied for numerically solving levitation problem based on eddy current. The main focus behind this coupled analysis method is to det
Externí odkaz:
http://arxiv.org/abs/2108.09632
Autor:
Sarkar, Sayan, Ghosh, Aayushman
Publikováno v:
In Biomedical Signal Processing and Control August 2024 94
HO-3D is a dataset providing image sequences of various hand-object interaction scenarios annotated with the 3D pose of the hand and the object and was originally introduced as HO-3D_v2. The annotations were obtained automatically using an optimizati
Externí odkaz:
http://arxiv.org/abs/2107.00887
We propose a robust and accurate method for estimating the 3D poses of two hands in close interaction from a single color image. This is a very challenging problem, as large occlusions and many confusions between the joints may happen. State-of-the-a
Externí odkaz:
http://arxiv.org/abs/2104.14639
Autor:
Hampali, Shreyas, Stekovic, Sinisa, Sarkar, Sayan Deb, Kumar, Chetan Srinivasa, Fraundorfer, Friedrich, Lepetit, Vincent
We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data. More exactly, we propose a modification of the Monte Carlo Tree Search (MCTS) algorithm to retrieve objects and room layouts from noisy
Externí odkaz:
http://arxiv.org/abs/2103.07969